Neural Network for Skeletons from Input Images

2. The system of claim 1, wherein processing the feature maps using the first head neural networks and processing the feature maps using the second head neural networks are executed in parallel such that the first head neural networks and the second head neural networks run concurrently.

4. The system of claim 1, wherein the input image includes overlapping bodies, the processor being further configured to receive, as input, a pair of skeletons and output a confidence score indicating a probability that each skeleton in the pair of skeletons belongs to a same body in the input image.

6. The system of claim 1, wherein the concatenated pyramid network includes a residual neural network including a plurality of intermediate layers that are configured as convolutional neural network layers, the plurality of intermediate layers connected on a downstream side to a concatenation layer and a plurality of convolutional layers, in this order.

7. The system of claim 1, wherein the plurality of first head neural networks and the plurality of second head neural networks each includes a fully convolutional neural network including a plurality of convolutional layers.

8. The system of claim 1, wherein the input image is from real-time input received from a visible light camera, a depth camera, or an infrared camera, and the processor is configured so that the outputting of the one or more instances of virtual skeletons from the input image received in real time is output in real time.

9. The system of claim 1, wherein the input image includes one or more of visible light image data, depth data, and active brightness data.

10. The system of claim 1, wherein linking the keypoints is performed by a greedy algorithm by fitting keypoint locations and part affinity field locations to form each instance of the one or more instances of the virtual skeletons, and linking the keypoints is repeated to maximize a total fitting score for each instance of the one or more instances of the virtual skeletons.

11. The system of claim 1, wherein the training data set includes human body part localization and association data and a keypoint dataset, and the convolutional neural network is trained for a single stage.

13. The computing method of claim 12, wherein processing the feature maps using the first head neural networks and processing the feature maps using the second head neural networks are executed in parallel such that the first head neural networks and the second head neural networks run concurrently.

16. The computing method of claim 12, wherein the concatenated pyramid network includes a residual neural network including a plurality of intermediate layers that are configured as convolutional neural network layers, the plurality of intermediate layers connected on a downstream side to a concatenation layer and a plurality of convolutional layers, in this order.

17. The computing method of claim 12, wherein the plurality of first head neural networks and the plurality of second head neural networks each includes a fully convolutional neural network including a plurality of convolutional layers.

18. The computing method of claim 12, wherein the input image is from real-time input received from a visible light camera, a depth camera, or an infrared camera, and the processor is configured so that the outputting of the one or more instances of virtual skeletons from the input image received in real time is output in real time.

19. The computing method of claim 12, wherein the training data set includes human body part localization and association data and a keypoint dataset, and the convolutional neural network is trained for a single stage.